© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13903
    Prev
    Next
    INDEX
    Explanations

    lottery, guarantee, market, crypto

    np_acts-logits-general · gemini-2.5-flash-lite

    fire, bug, hire, limits, transactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     แต่
    0.40
     but
    0.39
     אבל
    0.38
    亚
    0.37
    오
    0.36
     구해
    0.36
    ین
    0.35
     е
    0.35
    بط
    0.35
     판
    0.35
    POSITIVE LOGITS
     Jeśli
    0.45
    如果你
    0.42
    Якщо
    0.41
    »:
    0.41
    Jeśli
    0.41
     stipulates
    0.41
     Согласно
    0.40
    zechoslovak
    0.39
    ঞ্চি
    0.39
    Ҫ
    0.38
    Activations Density 0.000%

    No Known Activations